© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10127
    Prev
    Next
    INDEX
    Explanations

    pson

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pson
    -1.68
     humanities
    -0.92
    PSON
    -0.77
    gebnis
    -0.56
    τυχ
    -0.55
     golfe
    -0.55
    caro
    -0.54
    tispiece
    -0.53
    <?>>
    -0.53
    gebn
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.70
    tvguidetime
    0.63
    SharedCtor
    0.55
     <>",
    0.53
     חיצוניים
    0.53
     ویکی‌پدیا
    0.52
    нинград
    0.50
    ">—
    0.49
    extendable
    0.48
     nahilalakip
    0.48
    Activations Density 0.015%

    No Known Activations